grosenthal commited on
Commit
446517e
1 Parent(s): ad1b430

Upload tokenizer

Browse files
Files changed (5) hide show
  1. source.spm +0 -0
  2. special_tokens_map.json +5 -0
  3. target.spm +0 -0
  4. tokenizer_config.json +12 -0
  5. vocab.json +0 -0
source.spm ADDED
Binary file (800 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (779 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "pad_token": "<pad>",
5
+ "separate_vocabs": false,
6
+ "source_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la",
7
+ "sp_model_kwargs": {},
8
+ "special_tokens_map_file": null,
9
+ "target_lang": "en",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff